© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7184
    Prev
    Next
    INDEX
    Explanations

    references to "Dark" as it relates to various contexts, indicating a focus on themes of darkness or dark matter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "dark"

    np_acts-logits-general · gemini-2.0-flash

    dark Matter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cotch
    -0.84
    yntaxException
    -0.80
     ujednoznacz
    -0.79
    ANEOUS
    -0.77
     propOrder
    -0.75
     Roskov
    -0.70
    aneous
    -0.70
     NSCoder
    -0.69
     MainAxisSize
    -0.67
    országban
    -0.64
    POSITIVE LOGITS
     dark
    0.88
     Dark
    0.81
     DARK
    0.79
    DARK
    0.78
    Dark
    0.76
    dark
    0.71
     oscuro
    0.68
    ened
    0.60
     brown
    0.58
     matter
    0.58
    Activations Density 0.052%

    No Known Activations